Janus-Shiau / lookahead_tensorflowLinks
Lookahead optimizer ("Lookahead Optimizer: k steps forward, 1 step back") for tensorflow
☆25Updated 5 years ago
Alternatives and similar repositories for lookahead_tensorflow
Users that are interested in lookahead_tensorflow are comparing it to the libraries listed below
Sorting:
- wrapping a keras optimizer to implement gradient accumulation☆119Updated 4 years ago
- tf2.0 implementation of circle loss☆32Updated 5 years ago
- Tensorflow version implementation of focal loss for binary and multi classification☆110Updated 6 years ago
- Focal Loss of multi-classification in tensorflow☆81Updated 6 years ago
- Octave convolution☆34Updated 3 years ago
- Try to use tf.estimator and tf.data together to train a cnn model.☆79Updated 6 years ago
- RAdam optimizer for keras☆71Updated 5 years ago
- Keras implement of Lazy optimizer☆21Updated 5 years ago
- saving memory by recomputing for keras☆37Updated 5 years ago
- lookahead optimizer for keras☆170Updated 5 years ago
- AutoTorch, A HPO Toolkit☆60Updated 5 years ago
- ☆31Updated 5 years ago
- 高性能小模型测评 Shared Tasks in NLPCC 2020. Task 1 - Light Pre-Training Chinese Language Model for NLP Task☆58Updated 5 years ago
- ☆24Updated 6 years ago
- Converting A PyTorch Model to Tensorflow pb using ONNX☆160Updated 5 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 5 years ago
- Simple Tensorflow implementation of "Adaptive Gradient Methods with Dynamic Bound of Learning Rate" (ICLR 2019)☆150Updated 6 years ago
- bert-of-theseus via bert4keras☆31Updated 4 years ago
- Multi Task Learning Implementation with Homoscedastic Uncertainty in Tensorflow☆53Updated 6 years ago
- Training RNNs as fast as CNNs. An unofficial tensorflow implementation.☆32Updated 7 years ago
- The implementation of focal loss proposed on "Focal Loss for Dense Object Detection" by KM He and support for multi-label dataset.☆313Updated 7 years ago
- An environment for testing tensorflow models.☆14Updated 7 years ago
- A GPU devices manager to choice freest gpu.☆133Updated 6 years ago
- Densely Connected CNN with Multi-scale Feature Attention for Text Classification☆132Updated 6 years ago
- Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization☆183Updated 3 years ago
- Train CNN model by tf.estimator☆29Updated 6 years ago
- ☆26Updated 5 years ago
- Cyclic learning rate TensorFlow implementation.☆66Updated 6 years ago
- Laozhongyi is an automatic hyperparameter tuning program based on grid search and simulated annealing.☆51Updated 2 years ago
- A simple demo of distributed training in Pytorch☆36Updated 5 years ago